AMD Radeon RX 5600 XT vs AMD Radeon RX 590 Comparison

The AMD Radeon RX 590 and AMD Radeon RX 5600 XT represent two distinct generations of AMD graphics hardware, with the former based on the Polaris 30 chip and the latter on the Navi 10 chip. The recorded data shows a clear performance hierarchy between them, but the differences extend far beyond raw speed into architecture, memory, and feature support. This analysis draws exclusively from benchmark results and specification data in the database to provide a neutral comparison.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon RX 590 holds an average benchmark score of 24,744, while the AMD Radeon RX 5600 XT scores 20,713. The RX 590 is about 19.5% higher in this aggregate metric, placing it in the 70th percentile of all GPUs versus the 66th percentile for the RX 5600 XT.

Q: How do the two cards compare in the 3DMark Steel Nomad DX12 test?

A: The RX 5600 XT scores 1,669, while the RX 590 scores 1,081. The RX 5600 XT leads by 54.4% in this specific test, which is a substantial margin favoring the newer architecture.

Q: What are the memory specifications of each card?

A: The RX 590 uses 8 GB of GDDR5 memory on a 256-bit bus, yielding a bandwidth of 256.0 GB/s. The RX 5600 XT uses 6 GB of GDDR6 memory on a 192-bit bus, yielding a higher bandwidth of 288.0 GB/s despite the smaller capacity and narrower bus.

Q: Which card has a higher boost clock speed?

A: The RX 5600 XT boosts to 1560 MHz, slightly above the RX 590’s boost of 1545 MHz. However, the RX 590 has a much higher base clock at 1469 MHz compared to the RX 5600 XT’s 1130 MHz.

Q: Are there differences in API support?

A: Yes. The RX 590 supports DirectX 12 (12_0) and Vulkan 1.3, while the RX 5600 XT supports DirectX 12 (12_1) and Vulkan 1.4. Both support OpenGL 4.6.

Q: What is the power draw difference between the two?

A: The RX 590 has a TDP of 175 W, while the RX 5600 XT has a TDP of 150 W. Both use the same 450 W suggested PSU and a single 8-pin power connector.

The Verdict

Based on the recorded data, the AMD Radeon RX 5600 XT is the stronger performer in the two head-to-head benchmark tests available. It wins both tests, with substantial margins in the 3DMark Steel Nomad DX12 and Geekbench Metal workloads. The RX 5600 XT also offers a more modern feature set, including PCIe 4.0 x16, DirectX 12_1 support, and a 7 nm process node, all of which suggest better future-proofing for newer software titles.

However, the AMD Radeon RX 590 has its own merits. Its average benchmark score is higher, driven by a broader set of measurements that include legacy tests not available for the RX 5600 XT in the database. For users running older DirectX 9, 10, or 11 applications, the RX 590’s recorded scores may be more relevant, though direct comparisons in those tests are not present in the head-to-head data. The RX 590 also has a larger memory pool at 8 GB, which could benefit workloads that exceed the RX 5600 XT’s 6 GB capacity.

The choice depends on the workload. For pure performance in the two recorded head-to-head tests, the RX 5600 XT is the clear winner, delivering a 35.2% advantage in 3DMark Steel Nomad DX12 and a 39.8% advantage in Geekbench Metal. For users prioritizing higher aggregate benchmark scores or requiring more VRAM capacity, the RX 590 appears more favorable. Neither card is currently in production, as both are marked end-of-life.

Head-to-Head Benchmarks

The database provides two direct comparisons between these cards. In the 3DMark Steel Nomad DX12 test, the RX 5600 XT scores 1,669, while the RX 590 scores 1,081. The difference translates to a 35.2% lead for the RX 5600 XT. This is a significant gap, and it likely reflects the architectural improvements in RDNA 1.0 over GCN 4.0, particularly in how the former handles modern DirectX 12 workloads. The RX 5600 XT’s higher pixel rate (99.84 GPixel/s versus 49.44 GPixel/s) is consistent with this result, as it suggests better fill-rate efficiency under load.

In the Geekbench Metal test, the RX 5600 XT scores 80,376, while the RX 590 scores 48,407. The RX 5600 XT leads by 39.8% in this compute-oriented benchmark. This test measures GPU compute performance in Metal, and the RX 5600 XT’s fp16 output of 14.38 TFLOPS (2:1) is double the RX 590’s fp16 output of 7.119 TFLOPS (1:1). That explains why the RX 5600 XT excels in compute tasks that leverage half-precision math, while the RX 590’s fp16 performance is identical to its fp32 performance.

The RX 5600 XT also has a higher texture rate at 224.6 GTexel/s, slightly above the RX 590’s 222.5 GTexel/s. The advantage is narrow, but it indicates the RX 5600 XT can handle texture-heavy scenes marginally better. The RX 590’s fp32 output is 7.119 TFLOPS, while the RX 5600 XT is 7.188 TFLOPS, which is a small 1% lead for the RX 5600 XT. Despite this near-parity in raw fp32, the 3DMark and Metal tests show much larger gaps, suggesting that architectural efficiency, not just peak throughput, drives the final scores.

In the head-to-head results, the RX 5600 XT wins both tests, giving it a clean 2-0 record. The RX 590 has no wins in this dataset. This outcome is notable because the RX 590 has a higher overall average benchmark score, but that average includes scores from a broader set of tests, many of which are older API benchmarks (e.g., PassMark DirectX 9, 10, 11), which are absent for the RX 5600 XT. When isolated to the shared tests, the RX 5600 XT’s performance is superior.

Specification Differences

The two cards diverge on several key specifications. The RX 590 has a base clock of 1469 MHz and a boost clock of 1545 MHz, while the RX 5600 XT has a base clock of 1130 MHz, a game clock of 1375 MHz, and a boost clock of 1560 MHz. The RX 590’s base clock is 339 MHz higher, but the RX 5600 XT’s boost clock is 15 MHz higher. The game clock for the RX 5600 XT sits between its base and boost, which is a feature specific to its design.

Memory is another area of divergence. The RX 590 has 8 GB of GDDR5 memory, while the RX 5600 XT has 6 GB of GDDR6. The bus width varies as well, with the RX 590 using a 256-bit bus and the RX 5600 XT using a 192-bit bus. Despite the narrower bus, the RX 5600 XT achieves higher bandwidth (288.0 GB/s versus 256.0 GB/s) due to the faster GDDR6 memory running at 12 Gbps effective, compared to the RX 590’s 8 Gbps effective GDDR5. The memory clock for the RX 5600 XT is 1500 MHz, while the RX 590’s is 2000 MHz, but the effective data rate is what matters for bandwidth.

The pixel rate is nearly double for the RX 5600 XT at 99.84 GPixel/s versus 49.44 GPixel/s for the RX 590. This is because the RX 5600 XT has 64 ROPs, twice the 32 ROPs of the RX 590. Texture rate is similar (224.6 vs 222.5 GTexel/s), as both have 144 TMUs. The shading units are identical at 2,304.

The power draw differs, with the RX 590 at 175 W TDP and the RX 5600 XT at 150 W TDP, a 25 W reduction for the newer card. Both use dual-slot cooling and a single 8-pin power connector. The bus interface also differs: the RX 590 uses PCIe 3.0 x16, while the RX 5600 XT uses PCIe 4.0 x16. The card length varies, with the RX 590 at 241 mm and the RX 5600 XT at 267 mm.

Architecture Differences

The RX 590 is built on the Polaris 30 chip, which uses the GCN 4.0 architecture. The RX 5600 XT uses the Navi 10 chip with the RDNA 1.0 architecture. This is a fundamental difference in design philosophy. GCN 4.0 has been around since the Radeon RX 500 series, while RDNA 1.0 is a new approach that focuses on higher instructions per clock and better energy efficiency.

The manufacturing process differs significantly. The RX 590 is fabricated on a 12 nm process at GlobalFoundries, while the RX 5600 XT uses a 7 nm process at TSMC. The smaller node allows the RX 5600 XT to pack 10,300 million transistors into a 251 mm² die, compared to 5,700 million transistors in a 232 mm² die for the RX 590. This results in a transistor density of 41.0M per mm² for the RX 5600 XT versus 24.6M per mm² for the RX 590.

The RX 5600 XT’s FP16 performance is double its FP32 output at 14.38 TFLOPS, indicating a 2:1 ratio, while the RX 590’s FP16 is identical to its FP32 at 7.119 TFLOPS, a 1:1 ratio. This is a significant architectural difference, as the RX 5600 XT can accelerate certain compute workloads that take advantage of half-precision math, while the RX 590 does not offer such a boost.

The API support also reflects the newer architecture. The RX 5600 XT supports DirectX 12_1, which includes features like conservative rasterization and raster order views, while the RX 590 is limited to DirectX 12_0. Vulkan support is also newer on the RX 5600 XT (Vulkan 1.4) compared to the RX 590 (Vulkan 1.3). DirectX 12_1 support and the bus interface update to PCIe 4.0 on the RX 5600 XT are notable for compatibility with newer motherboards.

The RX 5600 XT’s pixel rate is twice the RX 590’s, which is tied to its 64 ROPs versus 32. The RX 590’s texture rate is slightly lower, but the difference is less than 1%. The transistor count more than doubles in the RX 5600 XT, but its die size is only 19 mm² larger, indicating the density of the 7 nm process. Both cards have no ray tracing or tensor cores, so those features are absent from both.

The production status is end-of-life for both, but the RX 590 was released on 2018-11-14, while the RX 5600 XT came later on 2020-01-20. The successor to the RX 590 is listed as Vega, while the RX 5600 XT’s successor is Navi II. The predecessor to the RX 590 is Arctic Islands, and for the RX 5600 XT it is Vega. The launch MSRP is identical for both at 279 USD, but this is historical data and not relevant to current availability.